library(tidyverse)
## ── Attaching packages ──────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0
## ── Conflicts ─────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(lubridate)
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
time_series_confirmed_long <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")) %>%
  rename(Province_State = "Province/State", Country_Region = "Country/Region")  %>% 
               pivot_longer(-c(Province_State, Country_Region, Lat, Long),
                             names_to = "Date", values_to = "Confirmed") 
## 
## ── Column specification ─────────────────────────────────────────
## cols(
##   .default = col_double(),
##   `Province/State` = col_character(),
##   `Country/Region` = col_character()
## )
## ℹ Use `spec()` for the full column specifications.
# Let's get the times series data for deaths
time_series_deaths_long <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv")) %>%
  rename(Province_State = "Province/State", Country_Region = "Country/Region")  %>% 
  pivot_longer(-c(Province_State, Country_Region, Lat, Long),
               names_to = "Date", values_to = "Deaths")
## 
## ── Column specification ─────────────────────────────────────────
## cols(
##   .default = col_double(),
##   `Province/State` = col_character(),
##   `Country/Region` = col_character()
## )
## ℹ Use `spec()` for the full column specifications.
# Create Keys 
time_series_confirmed_long <- time_series_confirmed_long %>% 
  unite(Key, Province_State, Country_Region, Date, sep = ".", remove = FALSE)
time_series_deaths_long <- time_series_deaths_long %>% 
  unite(Key, Province_State, Country_Region, Date, sep = ".") %>% 
  select(Key, Deaths)
# Join tables
time_series_long_joined <- full_join(time_series_confirmed_long,
    time_series_deaths_long, by = c("Key")) %>% 
    select(-Key)
# Reformat the data
time_series_long_joined$Date <- mdy(time_series_long_joined$Date)
# Create Report table with counts
time_series_long_joined_counts <- time_series_long_joined %>% 
  pivot_longer(-c(Province_State, Country_Region, Lat, Long, Date),
               names_to = "Report_Type", values_to = "Counts")
# Plot graph to a pdf outputfile
pdf("images/time_series_example_plot.pdf", width=6, height=3)
time_series_long_joined %>% 
  group_by(Country_Region,Date) %>% 
  summarise_at(c("Confirmed", "Deaths"), sum) %>% 
  filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
    geom_point() +
    geom_line() +
    ggtitle("US COVID-19 Deaths")
dev.off()
# Plot graph to a png outputfile
ppi <- 300
png("images/time_series_example_plot.png", width=6*ppi, height=6*ppi, res=ppi)
time_series_long_joined %>% 
  group_by(Country_Region,Date) %>% 
  summarise_at(c("Confirmed", "Deaths"), sum) %>% 
  filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
    geom_point() +
    geom_line() +
    ggtitle("US COVID-19 Deaths")
dev.off()
![US COVID-19 Deaths](images/time_series_example_plot.png) 
# This is an alternative way using html. 
# Remember that it must be in your working directory or you will need to specify the full path.
# The html is put OUTSIDE the r code chunk.

<img src="images/time_series_example_plot.png" alt="US COVID-19 Deaths" style="width: 600px;"/>
# Version 2
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
ggplotly(
  time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region == "US") %>% 
    ggplot(aes(x = Date,  y = Deaths)) + 
      geom_point() +
      geom_line() +
      ggtitle("US COVID-19 Deaths")
 )
library(plotly)
# Subset the time series data to include US deaths
US_deaths <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region == "US")
# Collect the layers for agraph of the US time series data for covid deaths
 p <- ggplot(data = US_deaths, aes(x = Date,  y = Deaths)) + 
        geom_point() +
        geom_line() +
        ggtitle("US COVID-19 Deaths")
# Plot the graph using ggplotly
ggplotly(p)
library(gganimate)
library(transformr)
library(gifski)
library(av)
theme_set(theme_bw())
data_time <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("China","Korea, South","Japan","Italy","US")) 
p <- ggplot(data_time, aes(x = Date,  y = Confirmed, color = Country_Region)) + 
      geom_point() +
      geom_line() +
      ggtitle("Confirmed COVID-19 Cases") +
      geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
animate(p, end_pause = 15)

data_time <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("China","Korea, South","Japan","Italy","US")) 
p <- ggplot(data_time, aes(x = Date,  y = Confirmed, color = Country_Region)) + 
      geom_point() +
      geom_line() +
      ggtitle("Confirmed COVID-19 Cases") +
      geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date) 
anim_save("deaths_5_countries.gif", p)

#Exercise 1

Top 10 Countries COVID-19 Deaths

ppi <- 300
png("Rplot01.png", width=3*ppi, height=3*ppi, res=ppi)

#Exercise 2

library(plotly)
# Subset the time series data to include US deaths
US_confirmed <- time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region == "US")
 p <- ggplot(data = US_confirmed, aes(x = Date,  y = Confirmed)) + 
        geom_point() +
        geom_line() +
        ggtitle("US COVID-19 Deaths")
# Plot the graph using ggplotly
ggplotly(p)

#Exercise 3

time_series_long_joined %>% 
    group_by(Country_Region,Date) %>% 
    summarise_at(c("Confirmed", "Deaths"), sum) %>% 
    filter (Country_Region %in% c("United Kingdom","France","Italy","Brazil", "India","Peru", "Spain", "Iran", "Mexico", "US"))
## # A tibble: 2,660 x 4
## # Groups:   Country_Region [10]
##    Country_Region Date       Confirmed Deaths
##    <chr>          <date>         <dbl>  <dbl>
##  1 Brazil         2020-01-22         0      0
##  2 Brazil         2020-01-23         0      0
##  3 Brazil         2020-01-24         0      0
##  4 Brazil         2020-01-25         0      0
##  5 Brazil         2020-01-26         0      0
##  6 Brazil         2020-01-27         0      0
##  7 Brazil         2020-01-28         0      0
##  8 Brazil         2020-01-29         0      0
##  9 Brazil         2020-01-30         0      0
## 10 Brazil         2020-01-31         0      0
## # … with 2,650 more rows
  p <- ggplot(data_time, aes(x = Date,  y = Confirmed, color = Country_Region)) + 
      geom_point() +
      geom_line() +
      ggtitle("Top 10 COuntries COVID-19 Deaths") +
      geom_point(aes(group = seq_along(Date))) +
      transition_reveal(Date)